Compute Library
 19.08
CLYOLOLayer Class Reference

Basic function to run CLYOLOLayerKernel that performs a partial activation on the input. More...

#include <CLYOLOLayer.h>

Collaboration diagram for CLYOLOLayer:
[legend]

Public Member Functions

void configure (ICLTensor *input, ICLTensor *output, const ActivationLayerInfo &act_info, int32_t num_classes)
 Set the input and output tensor. More...
 
- Public Member Functions inherited from ICLSimpleFunction
 ICLSimpleFunction ()
 Default constructor. More...
 
void run () override final
 Run the kernels contained in the function. More...
 
- Public Member Functions inherited from IFunction
virtual ~IFunction ()=default
 Destructor. More...
 
virtual void prepare ()
 Prepare the function for executing. More...
 

Static Public Member Functions

static Status validate (const ITensorInfo *input, const ITensorInfo *output, const ActivationLayerInfo &act_info, int32_t num_classes)
 Static function to check if given info will lead to a valid configuration of CLYOLOLayer. More...
 

Detailed Description

Basic function to run CLYOLOLayerKernel that performs a partial activation on the input.

For each box, activate only:

  • x and y position (channel 0 and 1 of each box)
  • objectiveness (channel 4 of each box)
  • classes (channel 5 to (classes - 5) of each box)

Definition at line 42 of file CLYOLOLayer.h.

Member Function Documentation

◆ configure()

void configure ( ICLTensor input,
ICLTensor output,
const ActivationLayerInfo act_info,
int32_t  num_classes 
)

Set the input and output tensor.

Note
If the output tensor is a nullptr or is equal to the input, the activation function will be performed in-place
Parameters
[in,out]inputSource tensor. In case of output tensor = nullptr, this tensor will store the result of the activation function. Data types supported: F16/F32.
[out]outputDestination tensor. Data type supported: same as input
[in]act_infoActivation layer parameters.
[in]num_classesNumber of classes to activate (must be submultiple of input channels)

Definition at line 32 of file CLYOLOLayer.cpp.

33 {
34  auto k = arm_compute::support::cpp14::make_unique<CLYOLOLayerKernel>();
35  k->configure(input, output, act_info, num_classes);
36  _kernel = std::move(k);
37 }

References arm_compute::test::validation::act_info.

◆ validate()

Status validate ( const ITensorInfo input,
const ITensorInfo output,
const ActivationLayerInfo act_info,
int32_t  num_classes 
)
static

Static function to check if given info will lead to a valid configuration of CLYOLOLayer.

Parameters
[in]inputSource tensor info. In case of output tensor info = nullptr, this tensor will store the result of the activation function. Data types supported: F16/F32.
[in]outputDestination tensor info. Data type supported: same as input
[in]act_infoActivation layer information.
[in]num_classesNumber of classes to activate (must be submultiple of input channels)
Returns
a status

Definition at line 39 of file CLYOLOLayer.cpp.

40 {
41  return CLYOLOLayerKernel::validate(input, output, act_info, num_classes);
42 }
static Status validate(const ITensorInfo *input, const ITensorInfo *output, const ActivationLayerInfo &act_info, int32_t num_classes)
Static function to check if given info will lead to a valid configuration of CLYOLOLayerKernel.

References arm_compute::test::validation::act_info, and CLYOLOLayerKernel::validate().


The documentation for this class was generated from the following files: